Stop wasting tokens on screenshots. Agent Browser helps AI agents browse the web using wireframe snapshots rather than screenshots or DOM dumps.
Browser Agents that communicate using ASCII wireframes
Stop wasting tokens on screenshots. Agent Browser helps AI agents browse the web using wireframe snapshots rather than screenshots or DOM dumps.
Currently AI browser agents send screenshots to the model. Each screenshot costs thousands of tokens. Over a multi-step task, that means high latency and high API cost. This package takes a different approach: it renders pages as ASCII wireframes with numbered elements. The agent sees [12]Sign Up instead of a 1280x720 image. Same information, far fewer tokens. It started as a way to make my own agents cheaper to run. Then I build a package around it. Fully open source and open to feedbacks!
Where do you see the biggest savings in token usage? Is it for when something is predominantly image heavy?
If someone is already using a Playwright-based MCP server (or a screenshot/vision-based computer-use setup), what’s the specific breaking point that typically makes them switch to Agent Browser, and what do they usually have to give up—if anything—in return for the token savings?
Great idea, best of luck with the launch :) looks very 1984 hacker vibe :) I love it and the practical applications seem very real especially for scraping etc
A measure of community engagement at launch. Higher means more people noticed and interacted with the product. It's a traction signal, not a quality rating.
Discussion threads divided by interest score. Above 0.30 is strong. Below 0.15 suggests the product got clicks but not conversation.
Categories come from the product's launch tags. Most products appear in 2-3 categories. The primary category is listed first.
The scores reflect launch-period engagement. Historical data is preserved and doesn't change retroactively. The build date at the bottom shows when the index was last refreshed.